Change Detection Method Research Articles

Comparison of Ratioing and RCNA Methods in the Detection of Flooded Areas Using Sentinel 2 Imagery (Case Study: Tulun, Russia)

Climate change and natural disasters caused by hydrological, meteorological, and climatic phenomena have a significant impact on cities. Russia, a continental country with a vast territory of complex geographic–ecological environments and highly variable climatic conditions, is subject to substantial and frequent natural disasters. On 29 June 2019, an extreme precipitation event occurred in the city of Tulun in the Irkutsk oblast, Russian Federation, which caused flooding due to the increase in the water level of the Iya River that passes through the city, leaving many infrastructures destroyed and thousands of people affected. This study aims to determine the flooded areas in the city of Tulun based on two change detection methods: Radiometric Rotation Controlled by No-change Axis (RCNA) and Ratioing, using Sentinel 2 images obtained before the event (19 June 2019) and during the flood peak (29 June 2019). The results obtained by the two methodologies were compared through cross-classification, and a 98% similarity was found in the classification of the areas. The study was validated based on photointerpretation of Google Earth images. The methodology presented proved to be useful for the automatic precession of flooded areas in a straightforward, but rigorous, manner. This allows stakeholders to efficiently manage areas that are buffeted by flooding episodes.

Detection of the Post-Earthquake Damage in Mamuju Regency in January 2021 Using Sentinel-1 Satellite Imagery

Friday, January 15 2021 at 02:28:21 Local Time, a tectonic earthquake with a magnitude of 6.2 occurred in Mamuju Regency. The epicenter of the earthquake was on land and at 38 km in depth, 6 km to the northeast of Majene, West Sulawesi Province. This earthquake has damaged buildings such as the West Sulawesi Governor’s Office, the Mitra Manakara Hospital, and landslides at several points on Mamuju – Majene highway. The purpose of this research is to determine the post-earthquake damage that occurred in Mamuju Regency and to find out the area that was detected because of the earthquake. By using Sentinel-1 satellite image data and the change detection method from two Sentinel-1 SAR images, ESA SNAP software is used for data processing by using a threshold classification on the images before and after the earthquake, then converting Raster to Vector, Clip according to the boundaries of Mamuju Regency and Layouts using ArcGIS software. The results of this study are the detection of the post-earthquake damage that occurred in Mamuju Regency of 100.64 km2 (14.78%) total area of damage detected. This research also obtained post-earthquake damage detection maps.

TRACKING THE URBAN CHAMELEON – TOWARDS A HYBRID CHANGE DETECTION OF GRAFFITI

Abstract. Colourful and ever-changing: Graffiti can be considered the urban chameleon skin. At the Donaukanal (Eng. Danube Channel), Vienna's central waterway and one of the largest and most active graffiti-scapes worldwide, this metaphor applies like hardly anywhere else. Every day a multitude of graffiti is destroyed by the creation of new works. Recently, efforts have been made to mitigate this constant loss of cultural heritage along the Donaukanal by systematically documenting the graffiti, mainly using photography and photogrammetry. However, keeping track of the newly added works is very time-consuming and often like finding needles in a haystack, considering the large extent and high volatility of the monitored area. Thus, an automated graffiti change detection would significantly reduce the effort and avoid overlooking graffiti.This contribution outlines the main challenges in image-based change detection for cultural heritage and proposes a hybrid graffiti change detection method. The investigated method exploits and combines an established pixel-based change detection algorithm, the Iteratively Multivariate Alteration Detection, with a novel descriptor-based method. The latter relies on image features, rather than pixels as analysis unit and can robustly filter false alarms from the high-performing but noise-prone pixel-based approach. Overall, the results indicate that the proposed method can largely automate image-based change detection of graffiti-scapes. It can uncover graffiti-related changes and robustly distinguish them from other image differences such as shadows but tends to overlook small-scale graffiti, indicating the need for further fine-tuning.

Qualitative and quantitative analysis of artificial neural network-based post-classification comparison to detect the earth surface variations using hyperspectral and multispectral datasets

Remote sensing is an effective way to analyze land surface changes on regular basis globally. In the previous literature, numerous change detection models were developed to detect the multitemporal or seasonal variations using different optical datasets, such as multispectral and hyperspectral. But there are many challenges involved in the processing of numerous bands, especially in the case of hyperspectral datasets, such as computational constraints and radiometric/atmospheric distortion. A simple framework-based artificial neural network (ANN) and post-classification comparison (PCC), named ANN-based PCC (ANPC), has been proposed to detect the multitemporal changes over agricultural land using hyperspectral, i.e., Earth Observation (EO-1) Hyperion and multispectral, i.e., Landsat-8. For cross-referencing, a comparative analysis is performed with respect to well-known PCC-based change detection methods, i.e., random forest-based post-comparison (RFPC) and support vector machine-based post-comparison (SVMPC). Experimental outcomes confirmed the effectiveness of ANPC (with an accuracy of more than 90%) in the extraction of multitemporal changes as compared to RFPC and SVMPC (with an accuracy of <90 % ). Our study enhances the utilization of the hyperspectral dataset (due to narrow spectral bands) in the extraction of critical information about the earth’s surface parameters.

Retrieving Soil Moisture at the Field Scale from Sentinel-1 Data over a Semi-Arid Mediterranean Agricultural Area

In this work, superficial soil moisture is estimated from SAR data at the field scale on agricultural fields over which the relationship between the co-polarized backscattering coefficient (γ0VV) and the measured soil moisture (SSMv) is both direct and inverse. An inversion algorithm is adapted to the charateristics of the single field and applied to SAR signal differences. The differences of SAR signal are obtained from a change detection (CD) method applied on the VV band of the Sentinel-1 SAR mission. In the CD method, the variations of the total backscattered signal due to sharp changes in vegetation and soil roughness are excluded from the dataset by using a machine learning algorithm. The retrieval method is applied on a low vegetated agricultural area in Spain, characterized by a semi-arid mediterranean climate and where in situ soil moisture data are available. Good results are obtained not only over fields characterized by direct γ0VV/SSMv relationship, reaching values of correlation coefficient and RMSE up to r=0.89 and RMSE=0.042 m3/m3, but also over fields with inverse relationship, obtaining in this case values up to r=0.84 ad RMSE=0.026 m3/m3. Although the inverse relationship between the backscattering coefficient and the measured soil moisture is not yet well understood in the field of soil moisture estimation from radar data, for the present case, checking the nature of this relationship was fundamental in order to accordingly adapt the soil moisture retrieval algorithm to the dataset characteristics.

Hybrid approach using deep learning and graph comparison for building change detection

ABSTRACT Existing methods of detecting building changes from very-high-resolution (VHR) images are limited by positional displacement. Although various change detection (CD) methods including deep learning methods have been proposed, they are incapable of overcoming the aforementioned limitation. Therefore, this study proposes a two-step hybrid approach using deep learning and graph comparison to detect building changes in VHR temporal images. First, the building objects were detected using mask regional-convolutional neural networks (Mask R-CNN), wherein the centroid of the bounding box was extracted as the building node. Second, for each image, graphs were generated using the extracted building nodes. Accordingly, the changed nodes were identified based on iterative graph comparison, which could be voluntarily halted without setting thresholds by examining the changes in the proposed index while sequentially eliminating the building changes. To demonstrate the effectiveness of the proposed method, we experimentally tested the simulated images with synthetic changes and positional displacements. The results verified that the proposed method effectively reduced the false detections originating from positional inconsistencies. Consequently, the proposed method could overcome the limitations of conventional CD methods by employing a graph model based on the connectivity between adjacent buildings.

Bi-Temporal change detection of high-resolution images by referencing time series medium-resolution images

ABSTRACT Seasonal changes usually exist and cause false alarms in the bi-temporal change detection from high-resolution remote sensing images. It is difficult to remove these false alarms only using bi-temporal images for traditional change detection methods. A change detection method is proposed to remove seasonal false alarms in bi-temporal change detection by introducing time series information of medium-resolution remote sensing images. First, the mid-resolution time series results are mapped to the ground objects obtained by multiscale segmentation of high-resolution remote sensing images. Second, set the thresholds for the proportion of each category of pixels in the object to obtain high-resolution time series results. Finally, the high-resolution change detection results are optimized by the improved high-resolution time series results. Experimental results show that this method can optimize the results of high-resolution change detection, and the accuracy of this method was improved by at least 0.23 than that of traditional change detection by reducing seasonal errors. The proposed method was an effective change detection approach for high-resolution images to reduce detection errors due to seasonal differences.

Mixed-former: multi-fusion remote sensing change detection

ABSTRACT Although remote sensing change detection methods based on deep learning have achieved relatively excellent results, they still face many challenges, such as many difficult samples and uneven sample distribution. The current CNN method is limited by the lack of effective global spatial-temporal information, while the transformer method is unable to accomplish the task of grounded application due to the complex network structure. Therefore, we propose mixedformer, a multi-fusion siamese network based on the enhancement of spatial-temporal information fusion. In this regard, the spatial-temporal symmetry module extracts valid potential contributing feature information based on a global self-attentive mechanism over the enhanced image information sequence. Because each embedding contains other embedding information, feature information can be generated at different locations to obtain denoised local feature information and global spatial-temporal information. At the same time, we argue that features in different layers, whether shallow or deep, contribute to the final detected change results with some weight. We also believe that both shallow and bottom features contribute some weight to the final detected change results. To achieve this, we use global cross-attention in the middle layer of decoding, linking valid information from deep and shallow layers, filtering noise from upsampling of the bottom features, while refining the edge information of the changes. Extensive experiments have shown that our model achieves excellent results on all three CD datasets with an appropriate amount of computation.

Change Detection in SAR Images through Clustering Fusion Algorithm and Deep Neural Networks

The detection of changes in synthetic aperture radar (SAR) images based on deep learning has been widely used in landslides detection, flood disaster monitoring, and other fields of change detection due to its high classification accuracy. However, the inherent speckle noise in SAR images restricts the performance of existing SAR image change detection algorithms by clustering analysis. Therefore, this paper proposes a novel method for SAR image change detection based on clustering fusion and deep neural networks. We first used hierarchical fuzzy c-means clustering (HFCM ) to process two different images to obtain HFCM classification results. Then a fusion strategy is designed to obtain the fused image from the two HFCM classified images as the pre-classification result. Furthermore, a lightweight deep neural network com posed of a decomposition convolution module and an auxiliary classification module was proposed; the former module could reduce network parameters by 28%, and the latter could reduce network parameters by 33.3%. To improve the recognition performance of the network, the classification layer was replaced by the regression layer at the outcome of the network. By comparing the experiments of different methods on five data sets, the performance of our proposed method is superior.

Consensus Techniques for Unsupervised Binary Change Detection Using Multi-Scale Segmentation Detectors for Land Cover Vegetation Images

Change detection in very-high-spatial-resolution (VHR) remote sensing images is a very challenging area with applicability in many problems ranging from damage assessment to land management and environmental monitoring. In this study, we investigated the change detection problem associated with analysing the vegetation corresponding to crops and natural ecosystems over VHR multispectral and hyperspectral images obtained by sensors onboard drones or satellites. The challenge of applying change detection methods to these images is the similar spectral signatures of the vegetation elements in the image. To solve this issue, a consensus multi-scale binary change detection technique based on the extraction of object-based features was developed. With the objective of capturing changes at different granularity levels taking advantage of the high spatial resolution of the VHR images and, as the segmentation operation is not well defined, we propose to use several detectors based on different segmentation algorithms, each applied at different scales. As the changes in vegetation also present high variability depending on capture conditions such as illumination, the use of the CVA-SAM applied at the segment level instead of at the pixel level is also proposed. The results revealed the effectiveness of the proposed approach for identifying changes over land cover vegetation images with different types of changes and different spatial and spectral resolutions.

Object-Oriented Remote Sensing Image Change Detection Based on Color Co-Occurrence Matrix

Aiming at the problem of misdetection caused by the traditional texture characteristic extraction model, which does not describe the correlation among multiple bands, an object-oriented remote sensing image change detection method based on a color co-occurrence matrix is proposed. First, the image is divided into multi-scale objects by graph-based superpixel segmentation, and the optimal scale is determined by the overall goodness F-measure (OGF). Then, except for the extraction of the spectral features, the multi-channel texture features based on the color co-occurrence matrix (CCM) are extracted to consider the correlation among multiple bands. To accurately find the representative features to overcome the impact of feature redundancy, a cumulative backward search strategy (CBSS) is further designed. Finally, the change detection is completed by inputting the difference image of dual time points to the trained random forest model. Taking Shenzhen and Dapeng as the study areas, with Sentinel-2 and Skysat images under different spatial resolutions, and the forest–bareland change type as an example, the effectiveness of the proposed algorithm is verified by qualitative and quantitative analyses. They show that the proposed algorithm can obtain higher detection accuracy than the texture features without band correlation.

DA-LSTM: A dynamic drift-adaptive learning framework for interval load forecasting with LSTM networks

Load forecasting is a crucial topic in energy management systems (EMS) due to its vital role in optimizing energy scheduling and enabling more flexible and intelligent power grid systems. As a result, these systems allow power utility companies to respond promptly to demands in the electricity market. Deep learning (DL) models have been commonly employed in load forecasting problems supported by adaptation mechanisms to cope with the changing pattern of consumption by customers, known as concept drift. A drift magnitude threshold should be defined to design change detection methods to identify drifts. While the drift magnitude in load forecasting problems can vary significantly over time, existing literature often assumes a fixed drift magnitude threshold, which should be dynamically adjusted rather than fixed during system evolution. To address this gap, in this paper, we propose a dynamic drift-adaptive Long Short-Term Memory (DA-LSTM) framework that can improve the performance of load forecasting models without requiring a drift threshold setting. We integrate several strategies into the framework based on active and passive adaptation approaches. To evaluate DA-LSTM in real-life settings, we thoroughly analyze the proposed framework and deploy it in a real-world problem through a cloud-based environment. Efficiency is evaluated in terms of the prediction performance of each approach and computational cost. The experiments show performance improvements on multiple evaluation metrics achieved by our framework compared to baseline methods from the literature. Finally, we present a trade-off analysis between prediction performance and computational costs.

A general and extensible framework for assessing change detection techniques

Change detection techniques play an essential role in Remote Sensing applications, such as environmental monitoring, governmental planning, and studies of areas affected by natural disasters. This fact makes the development of more accurate change detection techniques a constant challenge. However, the lack of public benchmarks available to analyze and compare the performance of change detection techniques hampers quantitative comparisons. In light of this reality, this study proposes and formalizes a novel framework for imagery dataset simulation. In contrast with other image simulation methods, images synthesized by the proposed method are explicitly designed to assess and compare change detection methods. The framework is extensible and general allowing, in particular, the use of both supervised and unsupervised change detection methods. As an application, we compare the performance of well-known algorithms to data sets that mimic what the Landsat 5 TM sensor observed over a forest area subjected to deforestation for agricultural purposes. The results support discussing the performance of methods and show the usefulness of the proposed framework. We provide the source codes in a public repository.

A Hierarchical Fusion SAR Image Change-Detection Method Based on HF-CRF Model

The mainstream methods for change detection in synthetic-aperture radar (SAR) images use difference images to define the initial change regions. However, methods can suffer from semantic collapse, which makes it difficult to determine semantic information about the changes. In this paper, we proposed a hierarchical fusion SAR image change-detection model based on hierarchical fusion conditional random field (HF-CRF). This model introduces multimodal difference images and constructs the fusion energy potential function using dynamic convolutional neural networks and sliding window entropy information. By using an iterative convergence process, the proposed method was able to accurately detect the change-detection regions. We designed a dynamic region convolutional semantic segmentation network with a two-branch structure (D-DRUNet) to accomplish feature fusion and the segmentation of multimodal difference images. The proposed network adopts a dual encoder–single decoder structure where the baseline is the UNet network that utilizes dynamic convolution kernels. D-DRUNet extracts multimodal difference features and completes semantic-level fusion. The Sobel operator is introduced to strengthen the multimodal difference-image boundary information and construct the dynamic fusion pairwise potential function, based on local boundary entropy. Finally, the final change result is stabilized by iterative convergence of the CRF energy potential function. Experimental results demonstrate that the proposed method outperforms existing methods in terms of the overall number of detection errors, and reduces the occurrence of false positives.

Methods comparison for detecting trends in herbicide monitoring time-series in streams

An inadvertent consequence of pesticide use is aquatic pesticide pollution, which has prompted the implementation of mitigation measures in many countries. Water quality monitoring programs are an important tool to evaluate the efficacy of these mitigation measures. However, large interannual variability of pesticide losses makes it challenging to detect significant improvements in water quality and to attribute these improvements to the application of specific mitigation measures. Thus, there is a gap in the literature that informs researchers and authorities regarding the number of years of aquatic pesticide monitoring or the effect size (e.g., loss reduction) that is required to detect significant trends in water quality. Our research addresses this issue by combining two exceptional empirical data sets with modelling to explore the relationships between the achieved pesticide reduction levels due to mitigation measures and the length of the observation period for establishing statistically significant trends. Our study includes both a large (Rhine at Basel, ∼36,300 km2) and small catchment (Eschibach, 1.2 km2), which represent spatial scales at either end of the spectrum that would be realistic for monitoring programs designed to assess water quality. Our results highlight several requirements in a monitoring program to allow for trend detection. Firstly, sufficient baseline monitoring is required before implementing mitigation measures. Secondly, the availability of pesticide use data helps account for the interannual variability and temporal trends, but such data are usually lacking. Finally, the timing and magnitude of hydrological events relative to pesticide application can obscure the observable effects of mitigation measures (especially in small catchments). Our results indicate that a strong reduction (i.e., 70–90 %) is needed to detect a change within 10 years of monitoring data. The trade-off in applying a more sensitive method for change detection is that it may be more prone to false-positives. Our results suggest that it is important to consider the trade-off between the sensitivity of trend detection and the risk of false positives when selecting an appropriate method and that applying more than one method can provide more confidence in trend detection.

A Statistical Analysis for Intensity Wavelength-Resolution SAR Difference Images

This paper presents a statistical analysis of intensity wavelength-resolution synthetic aperture radar (SAR) difference images. In this analysis, Anderson Darling goodness-of-fit tests are performed, considering two different statistical distributions as candidates for modeling the clutter-plus-noise, i.e., the background statistics. The results show that the Gamma distribution is a good fit for the background of the tested SAR images, especially when compared with the Exponential distribution. Based on the results of this statistical analysis, a change detection application for the detection of concealed targets is presented. The adequate selection of the background distribution allows for the evaluated change detection method to achieve a better performance in terms of probability of detection and false alarm rate, even when compared with competitive performance change detection methods in the literature. For instance, in an experimental evaluation considering a data set obtained by the Coherent All Radio Band Sensing (CARABAS) II UWB SAR system, the evaluated change detection method reached a detection probability of 0.981 for a false alarm rate of 1/km2.

An efficient change detection method for disaster-affected buildings based on a lightweight residual block in high-resolution remote sensing images

ABSTRACT After a natural disaster, it is critical to perform a damage assessment of affected buildings rapidly and accurately to meet emergency response requirements. With the development of deep learning (DL) technology, the change detection (CD) method based on fully convolutional networks has been used for disaster analysis and assessment. However, the main limitations of most present methods are their large number of parameters, high computational complexity, and limited deployment equipment resources, which affect the real-time performance of disaster analysis. Therefore, to make a trade-off in the relationship between the accuracy and efficiency of damaged building CD, this research proposes an efficient method based on a lightweight residual block (LRB) in bitemporal high-resolution remote sensing (RS) images (LRBNet). LRBNet is an encoder – decoder structure with the Siamese network and UNet++ as the backbone. It uses our LRB in the whole network to replace the original convolution unit, which can extract features to reduce computational complexity. The LRB consists of the lightweight compression module (LCM) and efficient channel attention (ECA) to learn the essential damage information in the feature map and improve the feature expression ability efficiently. Moreover, the multilevel damage feature aggregation attention module is the last process of the network and performs fine-grained aggregation of the multilevel disaster change features and emphasizes global semantic and spatial information to maximize the representative damage change characteristics. Furthermore, we conducted a series of experiments on the global-scale disaster xBD dataset (including 19 different disaster events). Our method not only accurately evaluated the level of disaster but also had favourable detection efficiency, achieving a good trade-off between recognition accuracy and computational resources.

DCAT: Dual Cross-Attention-Based Transformer for Change Detection

Several transformer-based methods for change detection (CD) in remote sensing images have been proposed, with Siamese-based methods showing promising results due to their two-stream feature extraction structure. However, these methods ignore the potential of the cross-attention mechanism to improve change feature discrimination and thus, may limit the final performance. Additionally, using either high-frequency-like fast change or low-frequency-like slow change alone may not effectively represent complex bi-temporal features. Given these limitations, we have developed a new approach that utilizes the dual cross-attention-transformer (DCAT) method. This method mimics the visual change observation procedure of human beings and interacts with and merges bi-temporal features. Unlike traditional Siamese-based CD frameworks, the proposed method extracts multi-scale features and models patch-wise change relationships by connecting a series of hierarchically structured dual cross-attention blocks (DCAB). DCAB is based on a hybrid dual branch mixer that combines convolution and transformer to extract and fuse local and global features. It calculates two types of cross-attention features to effectively learn comprehensive cues with both low- and high-frequency information input from paired CD images. This helps enhance discrimination between the changed and unchanged regions during feature extraction. The feature pyramid fusion network is more lightweight than the encoder and produces powerful multi-scale change representations by aggregating features from different layers. Experiments on four CD datasets demonstrate the advantages of DCAT architecture over other state-of-the-art methods.

Benchmarking Change Detector Algorithms from Different Concept Drift Perspectives

The stream mining paradigm has become increasingly popular due to the vast number of algorithms and methodologies it provides to address the current challenges of Internet of Things (IoT) and modern machine learning systems. Change detection algorithms, which focus on identifying drifts in the data distribution during the operation of a machine learning solution, are a crucial aspect of this paradigm. However, selecting the best change detection method for different types of concept drift can be challenging. This work aimed to provide a benchmark for four drift detection algorithms (EDDM, DDM, HDDMW, and HDDMA) for abrupt, gradual, and incremental drift types. To shed light on the capacity and possible trade-offs involved in selecting a concept drift algorithm, we compare their detection capability, detection time, and detection delay. The experiments were carried out using synthetic datasets, where various attributes, such as stream size, the amount of drifts, and drift duration can be controlled and manipulated on our generator of synthetic stream. Our results show that HDDMW provides the best trade-off among all performance indicators, demonstrating superior consistency in detecting abrupt drifts, but has suboptimal time consumption and a limited ability to detect incremental drifts. However, it outperforms other algorithms in detection delay for both abrupt and gradual drifts with an efficient detection performance and detection time performance.

Rotor imbalance detection and diagnosis in floating wind turbines by means of drivetrain condition monitoring

This paper presents a novel approach for detection and diagnosis of the rotor imbalance types pitch misalignment, yaw misalignment and mass imbalance by monitoring the drivetrain vibration response. Traditionally, only SCADA signals including nacelle accelerations, rotor speed and electrical power are utilized for this purpose, while drivetrain condition monitoring signals are mainly used for fault detection in gears and bearings. A diagnostic method is proposed using statistical change detection methods for fault detection, phase angle estimation for localizing the faulty blade, and physics-based decision criteria for fault classification. The proposed method is tested in a numerical case study with aeroelastic and drivetrain multi-body models of the 10 MW DTU reference wind turbine. The results suggest that drivetrain condition monitoring signals are particularly beneficial for detecting and diagnosing pitch misalignment, since this fault type uniquely induces periodic out-of-plane bending moments that excite drivetrain bending modes. Drivetrain signals improved the detection rate of a 1° pitch error from 19% to near 100% and reduced the standard error in locating the faulty blade from 71.5° to 11.2°. In addition, by using drivetrain vibration amplitudes as a decision criterion, all considered pitch error cases are correctly distinguished from other fault types.